| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMLU Professional Law (test) | COPRO | Accuracy80.43 | 3 | 19d ago | |
| MMLU HS World History (test) | PSAO_LLM | Accuracy95.38 | 3 | 19d ago | |
| MMLU College Medicine (test) | PSAO_LLM | Accuracy0.8644 | 3 | 19d ago | |
| ChineseSimpleQA 10-shot | ERNIE 5.0-Base | Accuracy90.09 | 3 | 3mo ago | |
| PopQA 10-shot | ERNIE 5.0-Base | Accuracy65.24 | 3 | 3mo ago | |
| PreciseWikiQA 10-shot | ERNIE 5.0-Base | Accuracy74.48 | 3 | 3mo ago |